agentleFS
Sign inStart free
jerry609jerry609/PaperBot/AGENTS.md

PaperBot

AGENTS.md108 starsChanged 8 months agoMITView on GitHub

This document is the working contract for contributors and coding agents in this repository. Follow it as the default behavior unless a task-specific instruction says otherwise. PaperBot is a mixed Python + Next.js project. Open http://localhost:3000 for the web app. Notes: - Integration tests live under tests/integration/. - Prefer deterministic tests and mock external APIs when possible. Do not edit generated/vendor directories: - web/.next/ - web/node_modules/ Bootstrap local env: Then fill required keys (for example OPENAI_API_KEY).

  • Reads credentials
  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository5 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Follow it as the default behavior unless a task-specific instruction says otherwise.

    line 4
  2. Distinctive:

    Prefer deterministic tests and mock external APIs when possible.

    line 62
  3. Very specific:

    Follow established patterns in web/src/

    line 72
  4. Distinctive:

    Keep Tailwind usage consistent with nearby components

    line 73
  5. Distinctive:

    Do not edit generated/vendor directories:

    line 75
  6. Distinctive:

    Keep edits local and avoid unrelated refactors.

    line 109
  7. Distinctive:

    Prefer fast, targeted checks before broad test runs.

    line 110
  8. Distinctive:

    If behavior changes, add or update tests.

    line 111
  9. Distinctive:

    When uncertain, document assumptions explicitly in the final note.

    line 112

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

This document is the working contract for contributors and coding agents in this repository. Follow it as the default behavior unless a task-specific instruction says otherwise.

1) Repository Overview

PaperBot is a mixed Python + Next.js project.

  • src/ - Python backend package (agents, workflows, API)
  • tests/ - pytest suite (unit + integration)
  • alembic/ + alembic.ini - SQLAlchemy/Alembic migrations
  • web/ - Next.js dashboard (DeepCode Studio + UI)
  • cli/ - CLI and terminal tooling
  • docs/ - design notes and plans (docs/PLAN.md)
  • asset/, public/ - static assets for docs/UI

2) Local Development

Backend (Python)

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python -m uvicorn src.paperbot.api.main:app --reload --port 8000

Web (Next.js)

cd web
npm install
npm run dev

Open http://localhost:3000 for the web app.

3) Build, Lint, and Test

Python

pytest
# or
pytest -q
python -m black .
python -m isort .
pyright

Web

cd web
npm run lint
npm run build

Notes:

  • Integration tests live under tests/integration/.
  • Prefer deterministic tests and mock external APIs when possible.

4) Style Conventions

Python

  • Black formatting, line-length = 100
  • isort with Black profile
  • Naming: snake_case for functions/variables, PascalCase for classes

TypeScript/React

  • Follow established patterns in web/src/
  • Keep Tailwind usage consistent with nearby components

Do not edit generated/vendor directories:

  • web/.next/
  • web/node_modules/

5) Commits and Pull Requests

Commits

Use Conventional Commits:

  • feat: ...
  • fix: ...
  • refactor: ...
  • docs: ...

Pull Requests

Each PR should include:

  • What changed and why
  • Any config/environment impact
  • Linked issue (if available)
  • Validation evidence (for example: pytest, npm run build)
  • Screenshots or clips for UI changes under web/

6) Configuration

Bootstrap local env:

cp env.example .env

Then fill required keys (for example OPENAI_API_KEY).

7) Agent Working Rules

  • Make the smallest safe change that satisfies the request.
  • Keep edits local and avoid unrelated refactors.
  • Prefer fast, targeted checks before broad test runs.
  • If behavior changes, add or update tests.
  • When uncertain, document assumptions explicitly in the final note.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free